Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A method for managing metadata at a control device, comprising: determining, from a cache page corresponding to user data, a first region for storing raw metadata of the user data, the raw metadata comprising address information for storing the user data in a storage system; in response to the user data being modified, determining updated metadata of the modified user data to update the raw metadata in the first region; copying the updated metadata to a high-speed memory shared by the control device and another control device; in response to metadata stored on a second region of the cache page being updated, merging the first region and the second region into a third region; and copying the metadata stored in the third region to the shared high-speed memory; wherein merging the first region and the second region into a third region comprises: determining a first starting position and a first length of the first region in the cache page; determining a second starting position and a second length of the second region in the cache page; determining a starting position of the third region based on the first starting position and the second starting position; and determining a length of the third region, based on the first starting position, the first length, the second starting position, and the second length.
This invention relates to data management in computing systems, specifically addressing the efficient handling of metadata associated with user data. The problem solved is the need to quickly update and synchronize metadata across multiple control devices, especially when user data is modified. The method involves a control device managing metadata. Initially, a specific area within a cache page, designated as a first region, is identified for storing raw metadata. This raw metadata includes crucial address information for locating the user data within a storage system. When the user data is modified, updated metadata reflecting these changes is generated. This updated metadata then replaces the existing raw metadata in the first region. To facilitate rapid access and sharing, the updated metadata is copied to a high-speed memory that is accessible by both the current control device and another control device. Additionally, the cache page contains a second region storing metadata. When the metadata in this second region is updated, a merging process occurs. The contents of the first region (containing the latest raw metadata) and the second region are combined into a third region. This merging operation involves calculating the starting positions and lengths of both the first and second regions within the cache page to determine the starting position and length of the combined third region. Finally, the consolidated metadata from the third region is also copied to the shared high-speed memory.
2. The method according to claim 1 , wherein determining the first region comprises: determining the first region in the cache page for storing the raw metadata, based on description information of the cache page.
3. The method according to claim 1 , wherein determining updated metadata of the modified user data comprises: determining, based on address mapping management information, address information of the modified user data stored in the storage system; and generating the updated metadata based on the determined address information.
4. The method according to claim 1 , further comprising: sending an update message to the another control device to inform the another control device to use the updated metadata that has been stored in the shared high-speed memory.
This invention relates to a system for managing and updating metadata in a distributed control environment, particularly where multiple control devices share access to a high-speed memory. The problem addressed is ensuring efficient and synchronized metadata updates across multiple control devices without disrupting ongoing operations. The system includes a primary control device that generates or receives updated metadata and stores it in a shared high-speed memory accessible by other control devices. The primary control device then sends an update message to the other control devices, instructing them to retrieve and use the updated metadata from the shared memory. This ensures all devices operate with the latest metadata while minimizing latency and avoiding conflicts. The shared high-speed memory allows for rapid access and synchronization, improving system performance and reliability. The update message may include identifiers or timestamps to ensure the correct metadata version is used. This approach is particularly useful in real-time control systems where timely metadata updates are critical for coordinated operation.
5. The method according to claim 1 , further comprising: in response to receiving an access request for the user data, redirecting the access request to one of the control device and the another control device based on address information of the user data to be accessed.
6. A control device for managing metadata, comprising: at least one processing unit; at least one memory coupled to the at least one processing unit and storing instructions executed by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the control device to perform actions comprising: determining, from a cache page corresponding to user data, a first region for storing raw metadata of the user data, the raw metadata including address information for storing the user data in a storage system; in response to the user data being modified, determining updated metadata of the modified user data to update the raw metadata in the first region; copying the updated metadata to a high-speed memory shared by the control device and another control device; in response to metadata stored on a second region of the cache page being updated, merging the first region and the second region into a third region; and copying the metadata stored in the third region to the shared high-speed memory; wherein merging the first region and the second region into a third region comprises: determining a first starting position and a first length of the first region in the cache page; determining a second starting position and a second length of the second region in the cache page; determining a starting position of the third region based on the first starting position and the second starting position; and determining a length of the third region, based on the first starting position, the first length, the second starting position, and the second length.
This invention relates to a control device for managing metadata in a storage system. The device addresses the challenge of efficiently handling metadata updates and ensuring consistency across multiple control devices in a distributed storage environment. The control device includes a processing unit and memory storing instructions to perform metadata management tasks. It determines a first region in a cache page for storing raw metadata, which includes address information for user data storage. When user data is modified, the device generates updated metadata and copies it to a high-speed memory shared with another control device. If metadata in a second region of the cache page is updated, the device merges the first and second regions into a third region. The merging process involves calculating the starting positions and lengths of the regions to form a contiguous third region. The merged metadata is then copied to the shared high-speed memory. This approach ensures efficient metadata updates and synchronization between control devices, improving storage system performance and reliability. The device dynamically adjusts metadata regions to optimize storage and access efficiency.
7. The control device according to claim 6 , wherein determining the first region comprises: determining the first region in the cache page for storing the raw metadata, based on description information of the cache page.
8. The control device according to claim 6 , wherein determining updated metadata of the modified user data comprises: determining, based on address mapping management information, address information of the modified user data stored in the storage system; and generating the updated metadata based on the determined address information.
9. The control device according to claim 6 , wherein the actions further comprise: sending an update message to the another control device to inform the another control device to use the updated metadata that has been stored in the shared high-speed memory.
10. The control device according to claim 6 , wherein the actions further comprise: in response to receiving an access request for the user data, redirecting the access request to one of the control device and the another control device based on address information of the user data to be accessed.
This invention relates to a control device for managing access to user data in a distributed system. The problem addressed is efficiently routing access requests to the correct control device in a system where user data may be distributed across multiple devices. The invention provides a control device that includes a processor and memory storing instructions for performing actions. These actions include receiving an access request for user data and redirecting the request to either the control device itself or another control device based on address information associated with the user data. The address information determines the appropriate destination for the request, ensuring that access is directed to the correct location. The control device may also include a communication interface for transmitting and receiving data, and a storage unit for storing user data. The system may involve multiple control devices, each capable of handling access requests and redirecting them as needed. This approach improves efficiency by minimizing unnecessary data transfers and ensuring that requests are routed to the correct device based on the data's location.
11. A computer program product having a non-transitory computer readable medium which stores a set of instructions to manage metadata at a control device; the set of instructions, when carried out by computerized circuitry, causing the computerized circuitry to perform a method of: determining, from a cache page corresponding to user data, a first region for storing raw metadata of the user data, the raw metadata comprising address information for storing the user data in a storage system; in response to the user data being modified, determining updated metadata of the modified user data to update the raw metadata in the first region; copying the updated metadata to a high-speed memory shared by the control device and another control device; in response to metadata stored on a second region of the cache page being updated, merging the first region and the second region into a third region; and copying the metadata stored in the third region to the shared high-speed memory; wherein merging the first region and the second region into a third region comprises: determining a first starting position and a first length of the first region in the cache page; determining a second starting position and a second length of the second region in the cache page; determining a starting position of the third region based on the first starting position and the second starting position; and determining a length of the third region, based on the first starting position, the first length, the second starting position, and the second length.
12. The computer program product according to claim 11 , wherein determining the first region comprises: determining the first region in the cache page for storing the raw metadata, based on description information of the cache page.
This invention relates to computer systems and methods for managing metadata storage in cache memory. The problem addressed is efficiently organizing and accessing raw metadata within a cache page to improve system performance and resource utilization. The invention provides a technique for determining a specific region within a cache page dedicated to storing raw metadata, using description information of the cache page to identify the appropriate storage location. The description information may include structural details, allocation rules, or other metadata-specific parameters that define how the cache page is partitioned. By dynamically assigning a region for raw metadata based on this description, the system ensures that metadata is stored in an optimal location, reducing access latency and improving cache efficiency. This approach is particularly useful in systems where metadata is frequently accessed or updated, as it minimizes the overhead associated with metadata management while maintaining data integrity and coherence. The invention may be implemented in various computing environments, including databases, file systems, and virtual memory systems, where efficient metadata handling is critical for overall system performance.
13. The computer program product according to claim 11 , wherein determining updated metadata of the modified user data comprises: determining, based on address mapping management information, address information of the modified user data stored in the storage system; and generating the updated metadata based on the determined address information.
14. The computer program product according to claim 11 , wherein the method further includes: sending an update message to the another control device to inform the another control device to use the updated metadata that has been stored in the shared high-speed memory.
15. The computer program product according to claim 11 , wherein the method further includes: in response to receiving an access request for the user data, redirecting the access request to one of the control device and the another control device based on address information of the user data to be accessed.
This invention relates to a computer program product for managing user data access in a distributed system. The problem addressed is efficiently routing access requests to the correct control device in a system where user data is distributed across multiple control devices. The solution involves a method that, upon receiving an access request for user data, redirects the request to the appropriate control device based on the address information of the requested data. This ensures that the request is directed to the control device that manages the specific data being accessed, improving system efficiency and reducing unnecessary processing. The method may also involve determining the address information of the user data, which could include identifying a storage location or a specific control device responsible for the data. The system may include multiple control devices, each managing different portions of user data, and the redirection is performed dynamically based on the address information to ensure accurate routing. This approach optimizes data access in distributed environments by minimizing latency and ensuring requests are handled by the correct control device.
16. A storage system, comprising: control devices constructed and arranged to access a set of storage devices; and a high-speed memory coupled with the control devices; each control device including: at least one processing unit; at least one memory coupled to the at least one processing unit and storing instructions executed by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the control device to perform actions comprising: determining, from a cache page corresponding to user data, a first region for storing raw metadata of the user data, the raw metadata including address information for storing the user data; in response to the user data being modified, determining updated metadata of the modified user data to update the raw metadata in the first region; copying the updated metadata to the high-speed memory; in response to metadata stored on a second region of the cache page being updated, merging the first region and the second region into a third region; and copying the metadata stored in the third region to the high-speed memory; wherein merging the first region and the second region into a third region comprises: determining a first starting position and a first length of the first region in the cache page; determining a second starting position and a second length of the second region in the cache page; determining a starting position of the third region based on the first starting position and the second starting position; and determining a length of the third region, based on the first starting position, the first length, the second starting position, and the second length.
17. The storage system according to claim 16 , wherein determining the first region comprises: determining the first region in the cache page for storing the raw metadata, based on description information of the cache page.
18. The storage system according to claim 16 , wherein determining updated metadata of the modified user data comprises: determining, based on address mapping management information, address information of the modified user data stored in the storage system; and generating the updated metadata based on the determined address information.
A storage system manages user data and associated metadata to ensure data integrity and efficient access. The system addresses challenges in tracking modifications to user data, particularly in distributed or complex storage environments where data locations may change. The invention provides a method for updating metadata when user data is modified, ensuring that the metadata accurately reflects the current state of the data. The system determines updated metadata for modified user data by first identifying the address information of the modified data within the storage system. This is done using address mapping management information, which tracks the locations of data blocks or files. The system then generates new metadata based on this address information, ensuring that the metadata remains consistent with the actual storage location of the data. This process helps maintain data integrity and enables efficient retrieval of the modified data. The solution is particularly useful in storage systems where data may be relocated or reorganized, such as in distributed storage, cloud storage, or systems with dynamic data allocation. By dynamically updating metadata based on address mapping information, the system ensures that metadata remains accurate and up-to-date, reducing the risk of data corruption or access errors. The approach improves reliability and performance in storage environments where data locations are subject to change.
19. The storage system according to claim 16 , wherein the actions further comprise: sending an update message to another control device to inform the another control device to use the updated metadata that has been stored in the high-speed memory.
20. The storage system according to claim 16 , wherein the actions further comprise: in response to receiving an access request for the user data, redirecting the access request to another control device based on address information of the user data to be accessed.
Unknown
March 2, 2021
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.